Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3050 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.3192. Min Act: -0.0002

Data Index: 782349 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.3043. Min Act: -0.0001

Data Index: 649158 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.3074. Min Act: -0.0001

Data Index: 309133 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2975. Min Act: -0.0001

Data Index: 73441 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1061606 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2995. Min Act: -0.0001

Data Index: 67058 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1120566 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2867. Min Act: -0.0001

Data Index: 73587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2831. Min Act: -0.0001

Data Index: 708791 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2847. Min Act: -0.0001

Data Index: 728121 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2831. Min Act: -0.0001

Data Index: 278190 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2898. Min Act: -0.0001

Data Index: 652444 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2857. Min Act: -0.0001

Data Index: 521916 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1132994 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2749. Min Act: -0.0001

Data Index: 971229 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1205200 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1127149 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2767. Min Act: -0.0001

Data Index: 589175 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2700. Min Act: -0.0001

Data Index: 240598 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2676. Min Act: -0.0001

Data Index: 816235 (C4 (Web Text))

Max Activating Token Index: 45